先思考再模拟：用于反事实问答的符号推理协调神经计算方法
Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering
AI总结：
针对神经符号模型反事实问答能力不足的问题，本文提出基于因果图与ASP符号推理协调感知和模拟模块的增强方法，在CLEVRER基准取得SOTA，结合大模型提示还可提升CRAFT基准反事实推理性能。
摘要：
对视频动态进行因果和时序推理是一项具有挑战性的问题。虽然将符号推理与基于神经网络的感知和预测相结合的神经符号模型已展现出应用前景，但它们存在局限性，尤其是在回答反事实问题方面。本文提出了一种增强神经符号模型反事实推理能力的方法，该方法利用对事件间因果关系的符号推理实现增强。我们定义了因果图的概念来表示这类关系，并采用 Answer Set Programming (ASP，回答集编程)——一种声明式逻辑编程方法——来确定如何协调感知模块和模拟模块。我们在 CLEVRER 和 CRAFT 两个基准上验证了所提方法的有效性。我们的增强方法在 CLEVRER 挑战赛上取得了当前最优性能，显著优于现有模型。在 CRAFT 基准的实验中，我们利用 GPT-3.5、GPT-4 等大型预训练语言模型作为动态模拟器的替代方案。研究结果表明，通过提供由符号因果推理生成的指导性替代提示，该方法能够进一步提升模型在反事实问题上的性能。
英文摘要：
Causal and temporal reasoning about video dynamics is a challenging problem. While neuro-symbolic models that combine symbolic reasoning with neural-based perception and prediction have shown promise, they exhibit limitations, especially in answering counterfactual questions. This paper introduces a method to enhance a neuro-symbolic model for counterfactual reasoning, leveraging symbolic reasoning about causal relations among events. We define the notion of a causal graph to represent such relations and use Answer Set Programming (ASP), a declarative logic programming method, to find how to coordinate perception and simulation modules. We validate the effectiveness of our approach on two benchmarks, CLEVRER and CRAFT. Our enhancement achieves state-of-the-art performance on the CLEVRER challenge, significantly outperforming existing models. In the case of the CRAFT benchmark, we leverage a large pre-trained language model, such as GPT-3.5 and GPT-4, as a proxy for a dynamics simulator. Our findings show that this method can further improve its performance on counterfactual questions by providing alternative prompts instructed by symbolic causal reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
